TensorRT installation problem

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Hello NVIDIA Team,

I got error when I install TensorRT 8 in ubuntu22.04 with TensorRT local repo file, “nv-tensorrt-local-repo-ubuntu2204-8.6.1-cuda-12.0_1.0-1_amd64.deb”.
The error is shown as:

$ sudo apt-get install tensorrt
Reading package lists… Done
Building dependency tree… Done
Reading state information… Done
Some packages could not be installed. This may mean that you have
requested an impossible situation or if you are using the unstable
distribution that some required packages have not yet been created
or been moved out of Incoming.
The following information may help to resolve the situation:

The following packages have unmet dependencies:

  • libnvinfer-dev : Depends: libcublas.so.12-dev but it is not installable*
  • libnvinfer-samples : Depends: libcudart.so.12-dev but it is not installable or*
  •                           cuda-cudart-cross-amd64-12-0 but it is not installable*

  •                  Depends: cuda-nvcc-12-1 but it is not installable or*

  •                           cuda-nvcc-12-0 but it is not installable*
  • libnvinfer8 : Depends: libcublas.so.12 but it is not installable*
    E: Unable to correct problems, you have held broken packages.

I can find “libcublas.so.12” in /usr/local/cuda-12.0/targets/x86_64-linux/lib.
I don’t know what does it mean and what is the relationship between “libcublas.so.12” and “libcublas.so.12-dev”.

Here is the Environment:

nvidia-smi
Fri Sep 1 14:52:16 2023
±----------------------------------------------------------------------------+
| NVIDIA-SMI 525.125.06 Driver Version: 525.125.06 CUDA Version: 12.0 |
|-------------------------------±---------------------±---------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA T600 Lap… Off | 00000000:01:00.0 Off | N/A |
| N/A 38C P0 9W / 40W | 5MiB / 4096MiB | 0% Default |
| | | N/A |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 2210 G /usr/lib/xorg/Xorg 4MiB |
±----------------------------------------------------------------------------+

nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Fri_Jan__6_16:45:21_PST_2023
Cuda compilation tools, release 12.0, V12.0.140
Build cuda_12.0.r12.0/compiler.32267302_0

CUDNN Version: 8500

Would you tell me how to solve the problem? Please let me know if any more detail is needed.

2

Hi,
Please refer to the installation steps from the below link if in case you are missing on anything

Also, we suggest you to use TRT NGC containers to avoid any system dependency related issues.

Thanks!

6

Have you managed to solve this error please?

7

same issue with Trt v8.6.1 GA
and cuda 11.8 ubuntu 22

8

Reinstall CUDA from .dev package, do not use that .run file. The .deb package contains all dependencies.

1 Like